© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15656
    Prev
    Next
    INDEX
    Explanations

    swallowing, ingestion, gulping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¿łå®ŀ
    -0.23
    ä¾ĿéĿł
    -0.19
    èĬ±å¼Ģ
    -0.19
    ëĨĢ
    -0.19
    åĽ´ç»ķ
    -0.19
    èĮķ
    -0.18
    æ°¾
    -0.18
    çĭ¬ç«ĭ
    -0.18
     Wit
    -0.17
    acent
    -0.17
    POSITIVE LOGITS
    åĴ½
    0.29
    ä¸Ģåı£
    0.23
    é£Łçī©
    0.20
    çĮĽ
    0.20
    åĻİ
    0.19
    chunks
    0.19
    ä¸ĢæĿ¯
    0.19
    liquid
    0.19
    heim
    0.19
    å®ĮäºĨ
    0.18
    Activations Density 0.012%

    No Known Activations